17 lines
450 B
Markdown
17 lines
450 B
Markdown
|
---
|
||
|
|
license: other
|
||
|
|
---
|
||
|
|
WizardLM-7B with 10k+ context using Landmark Attention.
|
||
|
|
|
||
|
|
Model generated using Landmark-Attention-QLoRA
|
||
|
|
|
||
|
|
https://github.com/eugenepentland/landmark-attention-qlora
|
||
|
|
|
||
|
|
|
||
|
|
A merge of the following models:
|
||
|
|
|
||
|
|
https://huggingface.co/TheBloke/wizardLM-7B-HF
|
||
|
|
|
||
|
|
https://huggingface.co/eugenepentland/WizardLM-7B-Landmark-Attention-QLoRA
|
||
|
|
|
||
|
|
Can be loaded in using oobooga, make sure to have the --trust-remote-code option on for it to function.
|